0 vs 1 benchmarks won
Anthropic Claude 2.1 | DeepSeek DeepSeek-V4-Pro | |
|---|---|---|
| Overview | ||
| Company | Anthropic | DeepSeek |
| Release date | Nov 21 2023 | Apr 24 2026 |
| Model type | — | — |
| Open source | No | Yes |
| Specifications | ||
Parameters | — | — |
Context window | — | — |
| Benchmarks | ||
Science reasoning GPQA Diamond | — | 90.1% |
Software engineering SWE-Bench Verified | — | — |
Multimodal understanding MMMU | — | — |
| Timeline | ||
| Release gap | Claude 2.1 shipped 885 days before DeepSeek-V4-Pro | |
DeepSeek-V4-Pro leads Claude 2.1 on 1 of the tracked benchmarks (GPQA Diamond, SWE-Bench Verified, MMMU). Claude 2.1 shipped 885 days before DeepSeek-V4-Pro, so benchmark comparisons should account for the intervening progress.
DeepSeek-V4-Pro is an open-source / open-weight model; Claude 2.1 is proprietary.
Direct benchmark comparisons are unavailable — at least one of these models has not published scores on GPQA Diamond, SWE-Bench Verified, or MMMU.